© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16259
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edale
    -0.09
    èĭį穹
    -0.07
    unders
    -0.07
    eszt
    -0.07
    çļĦåĩłä¸ª
    -0.07
    мп
    -0.07
    vand
    -0.07
    /results
    -0.07
    第åħŃå±Ĭ
    -0.07
    udara
    -0.07
    POSITIVE LOGITS
    æ¿
    0.08
     ith
    0.08
     denote
    0.07
     total
    0.07
    è®°
    0.07
    è®°åĪĨ
    0.07
    êu
    0.07
    åī¯æĢ»
    0.06
    çŁ¥éģĵåIJĹ
    0.06
    anned
    0.06
    Activations Density 0.003%

    No Known Activations